How long does the integration take?

Change one base URL in an OpenAI-compatible client, or install the Python or TypeScript SDK; the quickstart routes a first request in a few minutes.

Will this lock us into another vendor?

No. The router is Apache-2.0 open source, your provider keys stay yours, and the API is OpenAI-compatible, so leaving is a change of base URL.

What happens when a provider fails?

The router falls back to the next model your policy allows and records the fallback in the trace, so an outage costs a retry, not an incident.

reflect - Prompt - OpenSmartRoute

Name: reflect
Author: NikiforovAll

Prompt file imported from NikiforovAll/github-copilot-rules (.github/prompts/reflect.prompt.md). Fill in {{session_name}} before use. Copyright stays with the author.

Session Reflection

Create a reflective analysis of this AI coding session.

Purpose

Focus on META aspects - not what was implemented, but HOW the work was done:

Techniques and approaches used
What worked well vs. what didn't
Lessons learned for future sessions
Actionable improvements

Instructions

Analyze the Current Session

Review the conversation and identify:
- Problem-solving approaches used
- Tool/feature usage patterns (which worked well, which didn't)
- Communication patterns (clarifications, iterations)
- Planning and execution strategies
- Any blockers, pivots, or course corrections
Generate the Reflection

Create a markdown file at: _plans/reflections/<date>-<name>.md

Where:
- <date> is today's date in YYYY-MM-DD format
- <name> is a short kebab-case slug (2-4 words) from {{session_name}} or derived from the session gist (e.g., api-debugging, test-refactoring)
Use This Structure

# Session Reflection: [Brief Title]

**Date**: YYYY-MM-DD
**Session Goal**: [One-line summary of what the session aimed to accomplish]

---

## What Went Well

- [Effective technique or approach]
- [Tool usage that was particularly helpful]
- [Communication pattern that worked]

## What Went Wrong

- [Approach that didn't work or caused delays]
- [Tool misuse or inefficiency]
- [Unnecessary iteration or backtracking]

## Lessons Learned

1. **[Lesson Title]**: [Explanation of the insight and why it matters]
2. **[Lesson Title]**: [Explanation of the insight and why it matters]

## Action Items

- [ ] [Specific improvement to apply in future sessions]
- [ ] [Process or workflow change to consider]

## Tips & Tricks

Useful patterns discovered in this session:

- **Tip**: [Specific tip discovered or reinforced]
- **Tip**: [Another useful pattern or shortcut]

---

*Generated by `/reflect` prompt*

Guidelines

Be honest and specific - vague observations aren't actionable
Focus on process, not outcomes - "we used X approach" not "we built Y feature"
Prioritize actionable insights - each lesson should inform future behavior
Keep it concise - quality over quantity
Skip sections if not applicable - empty sections add no value

Examples

/reflect api-migration - Reflect on API migration session
/reflect - Auto-derive name from session gist

Install reflect and it becomes one more candidate the router can pick - when it fits.

A listing is a routing target with a manifest: what it does, which domains it covers, what it costs and who publishes it. Once installed it sits beside your own models and tools, is scored like any other candidate for each request, and shows up in the trace when it wins. Ratings come from workspaces that installed it, one per account.

# Session Reflection Create a reflective analysis of this AI coding session. ## Purpose Focus on **META aspects** - not what was implemented, but HOW the work was done: - Techniques and approaches used - What worked well vs. what didn't - Lessons learned for future sessions - Actionable improvements ## Instructions 1. **Analyze the Current Session** Review the conversation and identify: - Problem-solving approaches used - Tool/feature usage patterns (which worked well, which didn't) - Communication patterns (clarifications, iterations) - Planning and execution strategies - Any blockers, pivots, or course corrections 2. **Generate the Reflection** Create a markdown file at: `_plans/reflections/<date>-<name>.md` Where: - `<date>` is today's date in `YYYY-MM-DD` format - `<name>` is a short kebab-case slug (2-4 words) from `{{session_name}}` or derived from the session gist (e.g., `api-debugging`, `test-refactoring`) 3. **Use This Structure** ```markdown # Session Reflection: [Brief Title] **Date**: YYYY-MM-DD **Session Goal**: [One-line summary of what the session aimed to accomplish] --- ## What Went Well - [Effective technique or approach] - [Tool usage that was particularly helpful] - [Communication pattern that worked] ## What Went Wrong - [Approach that didn't work or caused delays] - [Tool misuse or inefficiency] - [Unnecessary iteration or backtracking] ## Lessons Learned 1. **[Lesson Title]**: [Explanation of the insight and why it matters] 2. **[Lesson Title]**: [Explanation of the insight and why it matters] ## Action Items - [ ] [Specific improvement to apply in future sessions] - [ ] [Process or workflow change to consider] ## Tips & Tricks Useful patterns discovered in this session: - **Tip**: [Specific tip discovered or reinforced] - **Tip**: [Another useful pattern or shortcut] --- *Generated by `/reflect` prompt* ``` ## Guidelines - **Be honest and specific** - vague observations aren't actionable - **Focus on process, not outcomes** - "we used X approach" not "we built Y feature" - **Prioritize actionable insights** - each lesson should inform future behavior - **Keep it concise** - quality over quantity - **Skip sections if not applicable** - empty sections add no value ## Examples - `/reflect api-migration` - Reflect on API migration session - `/reflect` - Auto-derive name from session gist

{ "prompt": "# Session Reflection\n\nCreate a reflective analysis of this AI coding session.\n\n## Purpose\n\nFocus on **META aspects** - not what was implemented, but HOW the work was done:\n- Techniques and approaches used\n- What worked well vs. what didn't\n- Lessons learned for future sessions\n- Actionable improvements\n\n## Instructions\n\n1. **Analyze the Current Session**\n\n Review the conversation and identify:\n - Problem-solving approaches used\n - Tool/feature usage patterns (which worked well, which didn't)\n - Communication patterns (clarifications, iterations)\n - Planning and execution strategies\n - Any blockers, pivots, or course corrections\n\n2. **Generate the Reflection**\n\n Create a markdown file at: `_plans/reflections/<date>-<name>.md`\n\n Where:\n - `<date>` is today's date in `YYYY-MM-DD` format\n - `<name>` is a short kebab-case slug (2-4 words) from `{{session_name}}` or derived from the session gist (e.g., `api-debugging`, `test-refactoring`)\n\n3. **Use This Structure**\n\n```markdown\n# Session Reflection: [Brief Title]\n\n**Date**: YYYY-MM-DD\n**Session Goal**: [One-line summary of what the session aimed to accomplish]\n\n---\n\n## What Went Well\n\n- [Effective technique or approach]\n- [Tool usage that was particularly helpful]\n- [Communication pattern that worked]\n\n## What Went Wrong\n\n- [Approach that didn't work or caused delays]\n- [Tool misuse or inefficiency]\n- [Unnecessary iteration or backtracking]\n\n## Lessons Learned\n\n1. **[Lesson Title]**: [Explanation of the insight and why it matters]\n2. **[Lesson Title]**: [Explanation of the insight and why it matters]\n\n## Action Items\n\n- [ ] [Specific improvement to apply in future sessions]\n- [ ] [Process or workflow change to consider]\n\n## Tips & Tricks\n\nUseful patterns discovered in this session:\n\n- **Tip**: [Specific tip discovered or reinforced]\n- **Tip**: [Another useful pattern or shortcut]\n\n---\n\n*Generated by `/reflect` prompt*\n```\n\n## Guidelines\n\n- **Be honest and specific** - vague observations aren't actionable\n- **Focus on process, not outcomes** - \"we used X approach\" not \"we built Y feature\"\n- **Prioritize actionable insights** - each lesson should inform future behavior\n- **Keep it concise** - quality over quantity\n- **Skip sections if not applicable** - empty sections add no value\n\n## Examples\n\n- `/reflect api-migration` - Reflect on API migration session\n- `/reflect` - Auto-derive name from session gist", "variables": [ "session_name" ], "notes": "Create reflective analysis of AI coding session for continuous improvement Arguments: Name or topic of the session to reflect on.", "metadata": { "source": { "provider": "github-prompts", "repository": "https://github.com/NikiforovAll/github-copilot-rules", "path": ".github/prompts/reflect.prompt.md", "ref": "f3fb825e0ce34dbefc1a3db19b2e81c102a47c4c", "url": "https://github.com/NikiforovAll/github-copilot-rules/blob/f3fb825e0ce34dbefc1a3db19b2e81c102a47c4c/.github/prompts/reflect.prompt.md", "key": "NikiforovAll/github-copilot-rules/.github/prompts/reflect.prompt.md" } } }

reflect

About

Session Reflection

Purpose

Instructions

Guidelines

Examples

Install reflect and it becomes one more candidate the router can pick - when it fits.

What it costs to adopt - in engineering time.

One base URL

No vendor lock-in

Failover built in

Use it

Manifest

Reviews